SCI 발표논문

SCI 발표논문

← SCI 발표논문 목록

Sci Rep. 2021;11(1):13026.

Predication of oxygen requirement in COVID-19 patients using dynamic change of inflammatory markers: CRP, hypertension, age, neutrophil and lymphocyte (CHANeL).

, , , , , , , , , , , ,

제1저자 이은영, 황우창 · 교신저자 김남중, 박진균

PMID 34158545 PMC8219792 DOI 10.1038/s41598-021-92418-2 IF 4.9 감염내과
소속 (12)
  1. Division of Rheumatology, Department of Internal Medicine, Uijeongbu Eulji Medical Center, Eulji University School of Medicine, Uijeongbu-Si, Gyeonggi-do, South Korea.
  2. Hanyang Biomedical Research Institute, Hanyang University, Seoul, South Korea.
  3. Division of Infectious Diseases, Department of Internal Medicine, Seoul National University Bundang Hospital, Seongnam, South Korea.
  4. Division of Infectious Diseases, Department of Internal Medicine, Seoul National University College of Medicine, 101, Daehak-ro, Jongno-gu, Seoul, 03080, South Korea.
  5. Division of Infectious Diseases, Department of Internal Medicine, Armed Forces Capital Hospital, Seongnam-Si, Gyeonggi-do, South Korea.
  6. Department of Infectious Diseases, Myongji Hospital, Goyang, Gyeonggi-do, South Korea.
  7. Department of Medical Education, Seoul National University College of Medicine, Seoul, South Korea.
  8. Division of Rheumatology, Department of Internal Medicine, Seoul National University Hospital and Seoul National University College of Medicine, 101, Daehak-ro, Jongno-gu, Seoul, 03080, South Korea.
  9. Division of Infectious Diseases, Department of Internal Medicine, National Medical Center, Seoul, South Korea.
  10. Department of Medicine, Major in Medical Genetics, Graduate School, Hanyang University, Seoul, South Korea.
  11. Division of Infectious Diseases, Department of Internal Medicine, Seoul National University College of Medicine, 101, Daehak-ro, Jongno-gu, Seoul, 03080, South Korea. molder@unitel.co.kr.
  12. Division of Rheumatology, Department of Internal Medicine, Seoul National University Hospital and Seoul National University College of Medicine, 101, Daehak-ro, Jongno-gu, Seoul, 03080, South Korea. jinkyunpark@gmail.com.

Abstract

The objective of the study was to develop and validate a prediction model that identifies COVID-19 patients at risk of requiring oxygen support based on five parameters: C-reactive protein (CRP), hypertension, age, and neutrophil and lymphocyte counts (CHANeL). This retrospective cohort study included 221 consecutive COVID-19 patients and the patients were randomly assigned randomly to a training set and a test set in a ratio of 1:1. Logistic regression, logistic LASSO regression, Random Forest, Support Vector Machine, and XGBoost analyses were performed based on age, hypertension status, serial CRP, and neutrophil and lymphocyte counts during the first 3 days of hospitalization. The ability of the model to predict oxygen requirement during hospitalization was tested. During hospitalization, 45 (41.8%) patients in the training set (n = 110) and 41 (36.9%) in the test set (n = 111) required supplementary oxygen support. The logistic LASSO regression model exhibited the highest AUC for the test set, with a sensitivity of 0.927 and a specificity of 0.814. An online risk calculator for oxygen requirement using CHANeL predictors was developed. "CHANeL" prediction models based on serial CRP, neutrophil, and lymphocyte counts during the first 3 days of hospitalization, along with age and hypertension status, provide a reliable estimate of the risk of supplement oxygen requirement among patients hospitalized with COVID-19.

Figures

Figure 1
Figure 1 Study design and patient flow. *National Medical Center (n = 128), Seoul National University Hospital (n = 46), Armed Forces Capital Hospital (n = 41), Myongji Hospital (n = 40), and Seoul National University Bundang Hospital (n = 25). ALC, absolute lymphocyte count; ANC, absolute neutrophil count; CRP, C-reactive protein.
Figure 2
Figure 2 Receiver operating characteristic curve (ROC) and radar plot showing the performance of five different prediction models. (A) ROC curve for the training set. (B) ROC curve for the test set. (C) Radar plot for the training set. (D) Radar plot for the test set. AUC, area under the curve; NPV, negative predictive value; PPV, positive predictive value.
Figure 3
Figure 3 CHANeL prediction model.

그림 출처: PubMed Central 공개 논문 (PMC8219792)

Conflict of interest statement

The authors declare no competing interests.

그 밖의 정보
출판 형태
Journal Article, Research Support, Non-U.S. Gov't
저널
Scientific reports · eISSN 2045-2322
전자 출판
2021-06-22
MeSH
Age Factors · Aged · Area Under Curve · Biomarkers / analysis / metabolism · C-Reactive Protein / analysis · COVID-19 / complications / pathology / virology · Female · Humans · Hypertension / complications · Logistic Models · Lymphocytes / cytology / metabolism · Male · Middle Aged · Neutrophils / cytology / metabolism · Oxygen Inhalation Therapy* · ROC Curve · Retrospective Studies · SARS-CoV-2 / isolation & purification · Severity of Illness Index · Support Vector Machine
Substances
Biomarkers · C-Reactive Protein
참고문헌
26편